© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1223
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on non-English (foreign-language) words, especially those with accented or unusual character sequences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    美国
    0.78
    畱
    0.78
    Historically
    0.77
    ଅ
    0.76
    荭
    0.76
    सामान्यीकृत
    0.75
    厛
    0.75
    文档
    0.75
    丽
    0.73
    毉
    0.73
    POSITIVE LOGITS
     nelle
    1.13
     quando
    1.08
     ώστε
    1.08
     desde
    1.07
     เพราะ
    1.07
     στις
    1.06
     durante
    1.05
     mentre
    1.05
     μέχρι
    1.05
     στην
    1.05
    Activations Density 0.091%

    No Known Activations